Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4779 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8451. Min Range: -1.8451

Max Act: 1.8451. Min Act: -0.0000

Data Index: 866163 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 1.8451. Min Range: -1.8451

Max Act: 1.2555. Min Act: -0.0000

Data Index: 46162 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.8451. Min Range: -1.8451

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1061263 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 1.8451. Min Range: -1.8451

Max Act: 1.0287. Min Act: -0.0000

Data Index: 336405 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.8451. Min Range: -1.8451

Max Act: 1.0220. Min Act: -0.0000

Data Index: 707693 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 1.8451. Min Range: -1.8451

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1149991 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1115977 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.9500. Min Act: -0.0000

Data Index: 688640 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1185709 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.9088. Min Act: -0.0000

Data Index: 636578 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.8819. Min Act: -0.0000

Data Index: 487459 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.8111. Min Act: -0.0000

Data Index: 706949 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.8681. Min Act: -0.0000

Data Index: 422592 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.8714. Min Act: -0.0000

Data Index: 550436 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.8237. Min Act: -0.0000

Data Index: 763704 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1074228 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1024135 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.7550. Min Act: -0.0000

Data Index: 241434 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1256782 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 1.8451. Min Range: -1.8451

Max Act: 0.8933. Min Act: -0.0000

Data Index: 652585 (C4 (Web Text))

Max Activating Token Index: 700